trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 12.190739124816034,
      "learning_rate": 6.666666666666666e-07,
      "loss": 2.3193,
      "step": 10
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 7.770064278169912,
      "learning_rate": 1.3333333333333332e-06,
      "loss": 2.1386,
      "step": 20
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 4.192906064331177,
      "learning_rate": 2e-06,
      "loss": 1.9414,
      "step": 30
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 3.3513942396767855,
      "learning_rate": 1.9510565162951534e-06,
      "loss": 1.7734,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 3.062516766803499,
      "learning_rate": 1.8090169943749474e-06,
      "loss": 1.7321,
      "step": 50
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 3.041537189390621,
      "learning_rate": 1.587785252292473e-06,
      "loss": 1.6518,
      "step": 60
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 3.0995357660927265,
      "learning_rate": 1.3090169943749473e-06,
      "loss": 1.6251,
      "step": 70
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 3.2094213343779003,
      "learning_rate": 1e-06,
      "loss": 1.5989,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 2.8948775712665835,
      "learning_rate": 6.909830056250526e-07,
      "loss": 1.6258,
      "step": 90
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.3079736744585913,
      "learning_rate": 4.1221474770752696e-07,
      "loss": 1.5466,
      "step": 100
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 3.0648068815310907,
      "learning_rate": 1.9098300562505264e-07,
      "loss": 1.5673,
      "step": 110
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 3.118857439456982,
      "learning_rate": 4.8943483704846465e-08,
      "loss": 1.5659,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.9540779821358494,
      "learning_rate": 0.0,
      "loss": 1.5773,
      "step": 130
    }
  ],
  "logging_steps": 10,
  "max_steps": 130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 18608453451776.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}